From Lukas-Kanade to Mnemonic Descent and Deep Dense Shape
Regression: A brief history of (deformable) image alignment.
Stefanos Zafeiriou
(Imperial College London, UK)
Abstract:
Construction and fitting of Statistical Deformable Models (SDM) is in the core
of computer vision and image analysis discipline. It can be used to estimate the
object's shape, pose, parts and landmarks using only static imagery captured
from monocular cameras. One of the first and most popular families of SDMs is
that of Active Appearance Models. AAM uses a generative parameterization of
object appearance and shape. The fitting process of AAMs is usually conducted by
solving a non-linear optimization problem. In this talk I will start with a
brief introduction to Lukas-Kanade and AAMs and I will continue with describing
supervised methods for AAM fitting. Subsequently, under this framework, I will
motivate current techniques developed in my group that capitalize on the
combined power of Deep Convolutional Neural Networks (DCNN) and Recurrent NN
(RNNs) for optimal deformable object modeling and fitting.
Bio:
Stefanos P. Zafeiriou (M'09) is currently a Senior Lecturer (USA equivalent to
Associate Professor) in Pattern Recognition/Statistical Machine Learning for
Computer Vision with the Department of Computing, Imperial College London,
London, U.K, and a Distinguishing Research Fellow with University of Oulu under
Finish Distinguishing Professor Programme. He was a recipient of the Prestigious
Junior Research Fellowships from Imperial College London in 2011 to start his
own independent research group. He was the recipient of the President's Medal
for Excellence in Research Supervision for 2016. He has received various awards
during his doctoral and post-doctoral studies. He currently serves as an
Associate Editor of the IEEE Transactions on Cybernetics the Image and Vision
Computing Journal. He has been a Guest Editor of over six journal special issues
and co-organised over nine workshops/special sessions on face analysis topics in
top venues, such as CVPR/FG/ICCV/ECCV (including two very successfully
challenges run in ICCV'13 and ICCV'15 on facial landmark
localisation/tracking). He has co-authored over 50 journal papers mainly on
novel statistical machine learning methodologies applied to computer vision
problems, such as 2-D/3-D face analysis, deformable object fitting and tracking,
shape from shading, and human behaviour analysis, published in the most
prestigious journals in his field of research, such as the IEEE T-PAMI, the
International Journal of Computer Vision, the IEEE T-IP, the IEEE T-NNLS, the
IEEE T-VCG, and the IEEE T-IFS, and many papers in top conferences, such as
CVPR, ICCV, ECCV, ICML. His students are frequent recipients of very prestigious
and highly competitive fellowships, such as the Google Fellowship, the Intel
Fellowship, and the Qualcomm Fellowship. He has more than 3300 citations to his
work, h-index 30. He is the General Chair of BMVC 2017.